danielhanchen commited on
Commit
5dacb43
·
verified ·
1 Parent(s): 501c7d1

Add files using upload-large-folder tool

Browse files
config.json CHANGED
@@ -3,38 +3,60 @@
3
  "Gemma3ForConditionalGeneration"
4
  ],
5
  "boi_token_index": 255999,
 
6
  "eoi_token_index": 256000,
7
- "eos_token_id": [
8
- 1,
9
- 106
10
- ],
11
  "image_token_index": 262144,
12
  "initializer_range": 0.02,
13
  "mm_tokens_per_image": 256,
14
  "model_type": "gemma3",
 
15
  "text_config": {
 
 
 
 
 
 
 
16
  "hidden_size": 3840,
 
17
  "intermediate_size": 15360,
 
18
  "model_type": "gemma3_text",
19
  "num_attention_heads": 16,
20
  "num_hidden_layers": 48,
21
  "num_key_value_heads": 8,
 
 
 
22
  "rope_scaling": {
23
  "factor": 8.0,
24
  "rope_type": "linear"
25
  },
26
- "sliding_window": 1024
 
 
 
 
 
27
  },
28
  "torch_dtype": "bfloat16",
29
- "transformers_version": "4.50.0.dev0",
 
30
  "vision_config": {
 
 
31
  "hidden_size": 1152,
32
  "image_size": 896,
33
  "intermediate_size": 4304,
 
34
  "model_type": "siglip_vision_model",
35
  "num_attention_heads": 16,
 
36
  "num_hidden_layers": 27,
37
  "patch_size": 14,
 
38
  "vision_use_head": false
39
  }
40
  }
 
3
  "Gemma3ForConditionalGeneration"
4
  ],
5
  "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
  "eoi_token_index": 256000,
8
+ "eos_token_id": 106,
 
 
 
9
  "image_token_index": 262144,
10
  "initializer_range": 0.02,
11
  "mm_tokens_per_image": 256,
12
  "model_type": "gemma3",
13
+ "pad_token_id": 0,
14
  "text_config": {
15
+ "attention_bias": false,
16
+ "attention_dropout": 0.0,
17
+ "attn_logit_softcapping": null,
18
+ "cache_implementation": "hybrid",
19
+ "final_logit_softcapping": null,
20
+ "head_dim": 256,
21
+ "hidden_activation": "gelu_pytorch_tanh",
22
  "hidden_size": 3840,
23
+ "initializer_range": 0.02,
24
  "intermediate_size": 15360,
25
+ "max_position_embeddings": 131072,
26
  "model_type": "gemma3_text",
27
  "num_attention_heads": 16,
28
  "num_hidden_layers": 48,
29
  "num_key_value_heads": 8,
30
+ "query_pre_attn_scalar": 256,
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_local_base_freq": 10000.0,
33
  "rope_scaling": {
34
  "factor": 8.0,
35
  "rope_type": "linear"
36
  },
37
+ "rope_theta": 1000000.0,
38
+ "sliding_window": 1024,
39
+ "sliding_window_pattern": 6,
40
+ "torch_dtype": "bfloat16",
41
+ "use_cache": true,
42
+ "vocab_size": 262208
43
  },
44
  "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.51.0",
46
+ "unsloth_fixed": true,
47
  "vision_config": {
48
+ "attention_dropout": 0.0,
49
+ "hidden_act": "gelu_pytorch_tanh",
50
  "hidden_size": 1152,
51
  "image_size": 896,
52
  "intermediate_size": 4304,
53
+ "layer_norm_eps": 1e-06,
54
  "model_type": "siglip_vision_model",
55
  "num_attention_heads": 16,
56
+ "num_channels": 3,
57
  "num_hidden_layers": 27,
58
  "patch_size": 14,
59
+ "torch_dtype": "bfloat16",
60
  "vision_use_head": false
61
  }
62
  }
generation_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "pad_token_id": 0,
10
  "top_k": 64,
11
  "top_p": 0.95,
12
- "transformers_version": "4.50.0.dev0"
13
  }
 
9
  "pad_token_id": 0,
10
  "top_k": 64,
11
  "top_p": 0.95,
12
+ "transformers_version": "4.51.0"
13
  }
special_tokens_map.json CHANGED
@@ -9,7 +9,7 @@
9
  },
10
  "eoi_token": "<end_of_image>",
11
  "eos_token": {
12
- "content": "<eos>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
9
  },
10
  "eoi_token": "<end_of_image>",
11
  "eos_token": {
12
+ "content": "<end_of_turn>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -51328,15 +51328,16 @@
51328
  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
51329
  "clean_up_tokenization_spaces": false,
51330
  "eoi_token": "<end_of_image>",
51331
- "eos_token": "<eos>",
51332
  "extra_special_tokens": {
51333
  "boi_token": "<start_of_image>",
51334
  "eoi_token": "<end_of_image>",
51335
  "image_token": "<image_soft_token>"
51336
  },
51337
  "image_token": "<image_soft_token>",
51338
- "model_max_length": 1000000000000000019884624838656,
51339
  "pad_token": "<pad>",
 
51340
  "processor_class": "Gemma3Processor",
51341
  "sp_model_kwargs": null,
51342
  "spaces_between_special_tokens": false,
 
51328
  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
51329
  "clean_up_tokenization_spaces": false,
51330
  "eoi_token": "<end_of_image>",
51331
+ "eos_token": "<end_of_turn>",
51332
  "extra_special_tokens": {
51333
  "boi_token": "<start_of_image>",
51334
  "eoi_token": "<end_of_image>",
51335
  "image_token": "<image_soft_token>"
51336
  },
51337
  "image_token": "<image_soft_token>",
51338
+ "model_max_length": 131072,
51339
  "pad_token": "<pad>",
51340
+ "padding_side": "left",
51341
  "processor_class": "Gemma3Processor",
51342
  "sp_model_kwargs": null,
51343
  "spaces_between_special_tokens": false,